refactor(#2464): rename hive-ag3nt crate to hive-agent, collapse lib into main

hive-agent/src/vacuum.rs

@@ -0,0 +1,133 @@
+//! Agent-side cleanup of this agent's own harness artifacts: completed
+//! bash-task files and verbose `stream` event rows.
+//!
+//! Runs IN the harness (not host-side in hive-c0re) because the files are
+//! owned by the agent user. Under privsep hive-c0re runs as the unprivileged
+//! `hive-core` user and cannot delete agent-owned files — the old host-side
+//! sweeps hit `PermissionDenied` on the bash-task trio and an
+//! attempt-to-write-a-readonly-database error on `events.sqlite`. The harness
+//! owns these paths, so the deletes succeed here.
+//!
+//! Trade-off (accepted — issue tracker "perms borked"): a misbehaving harness
+//! could skip its own cleanup, which the host-side version was meant to
+//! prevent. But a compromised harness is already inside the container trust
+//! boundary (`docs/security.md`), and these are ephemeral local artifacts — so
+//! the honest fix is to clean them up where they live.
+
+use std::path::Path;
+use std::time::Duration;
+
+use hive_sh4re::wire_time::now_unix;
+use rusqlite::{Connection, Result, params};
+
+/// How often the sweep runs.
+const VACUUM_INTERVAL: Duration = Duration::from_hours(1);
+/// Keep completed bash-task files this long before deleting their trio.
+const BASH_KEEP_SECS: i64 = 48 * 3600;
+/// Keep verbose `stream` event rows this long before pruning. Other event
+/// kinds are never deleted by this sweep — they carry the semantic per-turn
+/// history the operator scrolls back through.
+const STREAM_KEEP_SECS: i64 = 14 * 24 * 3600;
+/// Terminal bash-task statuses whose files are eligible for deletion.
+const TERMINAL_STATUSES: &[&str] = &["done", "timed_out", "interrupted"];
+
+/// Background loop: hourly, prune this agent's stale bash-task files and
+/// verbose event rows. Detached task — runs for the harness's lifetime;
+/// errors are logged, never fatal.
+pub async fn run() {
+    loop {
+        sweep_once();
+        tokio::time::sleep(VACUUM_INTERVAL).await;
+    }
+}
+
+fn sweep_once() {
+    let harness = crate::paths::harness_dir();
+
+    let tasks_dir = harness.join("bash-tasks");
+    if tasks_dir.is_dir() {
+        let removed = vacuum_bash_tasks(&tasks_dir, now_unix() - BASH_KEEP_SECS);
+        if removed > 0 {
+            tracing::info!(removed, "bash-tasks vacuum");
+        }
+    }
+
+    let events_db = harness.join("hyperhive-events.sqlite");
+    if events_db.exists() {
+        match vacuum_events(&events_db) {
+            Ok(0) => {}
+            Ok(n) => tracing::info!(removed = n, "events vacuum"),
+            Err(e) => tracing::warn!(error = ?e, "events vacuum failed"),
+        }
+    }
+}
+
+/// Delete eligible bash-task trios in `dir`. Returns the count of `.json`
+/// sentinels removed (each represents one task; `.out`/`.err` deletions are
+/// not counted separately).
+fn vacuum_bash_tasks(dir: &Path, cutoff: i64) -> u64 {
+    let Ok(rd) = std::fs::read_dir(dir) else {
+        return 0;
+    };
+    let mut removed: u64 = 0;
+    for entry in rd.flatten() {
+        let path = entry.path();
+        // Only process the .json sentinel; derive sibling paths from it.
+        if path.extension().and_then(|e| e.to_str()) != Some("json") {
+            continue;
+        }
+        let Some(stem) = path.file_stem().and_then(|s| s.to_str()).map(str::to_owned) else {
+            continue;
+        };
+        if should_delete(&path, cutoff) {
+            delete_trio(dir, &stem);
+            removed += 1;
+        }
+    }
+    removed
+}
+
+/// Return `true` when the task file has a terminal status and a
+/// `completed_at` older than `cutoff`.
+fn should_delete(json_path: &Path, cutoff: i64) -> bool {
+    let Ok(raw) = std::fs::read_to_string(json_path) else {
+        return false;
+    };
+    let Ok(v) = serde_json::from_str::<serde_json::Value>(&raw) else {
+        return false;
+    };
+    let status = v.get("status").and_then(|s| s.as_str()).unwrap_or("");
+    if !TERMINAL_STATUSES.contains(&status) {
+        return false;
+    }
+    let completed_at = v
+        .get("completed_at")
+        .and_then(serde_json::Value::as_i64)
+        .unwrap_or(i64::MAX);
+    completed_at < cutoff
+}
+
+/// Delete the `.json`, `.out`, and `.err` files for a task. Errors are
+/// logged but do not abort the sweep.
+fn delete_trio(dir: &Path, stem: &str) {
+    for ext in ["json", "out", "err"] {
+        let path = dir.join(format!("{stem}.{ext}"));
+        if path.exists()
+            && let Err(e) = std::fs::remove_file(&path)
+        {
+            tracing::warn!(path = %path.display(), error = ?e, "bash-tasks vacuum: remove failed");
+        }
+    }
+}
+
+/// Prune verbose `stream` event rows older than [`STREAM_KEEP_SECS`] from the
+/// agent's `events.sqlite`. Returns the number of rows deleted.
+fn vacuum_events(path: &Path) -> Result<u64> {
+    let conn = Connection::open(path)?;
+    let cutoff = now_unix() - STREAM_KEEP_SECS;
+    let removed = conn.execute(
+        "DELETE FROM events WHERE kind = 'stream' AND ts < ?1",
+        params![cutoff],
+    )?;
+    Ok(u64::try_from(removed).unwrap_or(0))
+}